#!/usr/bin/env python # -*- coding: utf-8 -*- """ Hidden layers for deep neural networks. Based on code from http://deeplearning.net/tutorial Author: M. Sam Ribeiro Date: 2017 """ import numpy import theano import theano.tensor as T class HiddenLayer(object): def __init__(self, rng, input, n_in, n_out, W=None, b=None, activation=T.tanh): """ Typical hidden layer of a MLP with fully-connected units. :type rng: numpy.random.RandomState :param rng: a random number generator used to initialize weights :type input: theano.tensor.dmatrix :param input: a symbolic tensor of shape (n_examples, n_in) :type n_in: int :param n_in: dimensionality of input :type n_out: int :param n_out: number of hidden units :type activation: theano.Op or function :param activation: Non linearity to be applied in the hidden layer """ self.input = input if W is None: W_values = numpy.asarray( rng.uniform( low=-numpy.sqrt(6. / (n_in + n_out)), high=numpy.sqrt(6. / (n_in + n_out)), size=(n_in, n_out) ), dtype=theano.config.floatX ) if activation == theano.tensor.nnet.sigmoid: W_values *= 4 W = theano.shared(value=W_values, name='W', borrow=True) if b is None: b_values = numpy.zeros((n_out,), dtype=theano.config.floatX) b = theano.shared(value=b_values, name='b', borrow=True) self.W = W self.b = b lin_output = T.dot(input, self.W) + self.b self.output = activation(lin_output) self.params = [self.W, self.b] class ConvPoolLayer(object): def __init__(self, rng, input, filter_shape, image_shape, poolsize=(2, 2)): """ Convolution and Pooling layer :type rng: numpy.random.RandomState :param rng: a random number generator used to initialize weights :type input: theano.tensor.dtensor4 :param input: symbolic image tensor, of shape image_shape :type filter_shape: tuple or list of length 4 :param filter_shape: (number of filters, num input feature maps, filter height, filter width) :type image_shape: tuple or list of length 4 :param image_shape: (batch size, num input feature maps, image height, image width) :type poolsize: tuple or list of length 2 :param poolsize: the downsampling (pooling) factor (#rows, #cols) """ assert image_shape[1] == filter_shape[1] self.input = input # there are "num input feature maps * filter height * filter width" # inputs to each hidden unit fan_in = numpy.prod(filter_shape[1:]) # each unit in the lower layer receives a gradient from: # "num output feature maps * filter height * filter width" / # pooling size fan_out = (filter_shape[0] * numpy.prod(filter_shape[2:]) // numpy.prod(poolsize)) # initialize weights with random weights W_bound = numpy.sqrt(6. / (fan_in + fan_out)) self.W = theano.shared( numpy.asarray( rng.uniform(low=-W_bound, high=W_bound, size=filter_shape), dtype=theano.config.floatX ), borrow=True ) # the bias is a 1D tensor -- one bias per output feature map b_values = numpy.zeros((filter_shape[0],), dtype=theano.config.floatX) self.b = theano.shared(value=b_values, borrow=True) # convolve input feature maps with filters conv_out = conv2d( input=input, filters=self.W, filter_shape=filter_shape, input_shape=image_shape ) # pool each feature map individually, using maxpooling pooled_out = pool.pool_2d( input=conv_out, ds=poolsize, ignore_border=True ) # add the bias term. Since the bias is a vector (1D array), we first # reshape it to a tensor of shape (1, n_filters, 1, 1). Each bias will # thus be broadcasted across mini-batches and feature map # width & height self.output = T.tanh(pooled_out + self.b.dimshuffle('x', 0, 'x', 'x')) # store parameters of this layer self.params = [self.W, self.b] # keep track of model input self.input = input